{"id":"https://openalex.org/W4224931714","doi":"https://doi.org/10.1109/icassp43922.2022.9746227","title":"Alignment-Learning Based Single-Step Decoding for Accurate and Fast Non-Autoregressive Speech Recognition","display_name":"Alignment-Learning Based Single-Step Decoding for Accurate and Fast Non-Autoregressive Speech Recognition","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224931714","doi":"https://doi.org/10.1109/icassp43922.2022.9746227"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746227","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008226894","display_name":"Yonghe Wang","orcid":"https://orcid.org/0000-0003-1647-1539"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghe Wang","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China","National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China","Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","College of Computer Science, Inner Mongolia University, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China","institution_ids":[]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082746577","display_name":"Rui Liu","orcid":"https://orcid.org/0000-0003-4524-7413"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Liu","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China","College of Computer Science, Inner Mongolia University, Hohhot, China","National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China","Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China","institution_ids":[]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014372166","display_name":"Feilong Bao","orcid":"https://orcid.org/0000-0001-7312-1629"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilong Bao","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China","College of Computer Science, Inner Mongolia University, Hohhot, China","Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]},{"raw_affiliation_string":"National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100323420","display_name":"Hui Zhang","orcid":"https://orcid.org/0000-0002-1803-3148"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Zhang","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China","Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","College of Computer Science, Inner Mongolia University, Hohhot, China","National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,Hohhot,China","College of Computer Science, Inner Mongolia University, Hohhot, China","Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"College of Computer Science, Inner Mongolia University, Hohhot, China","institution_ids":["https://openalex.org/I2722730"]},{"raw_affiliation_string":"Inner Mongolia Key Laboratory of Mongolian Information Processing Technology, Hohhot, China","institution_ids":[]},{"raw_affiliation_string":"National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian, Hohhot, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8292","last_page":"8296"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.8451477289199829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7808628082275391},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7464830875396729},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6602673530578613},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6058841943740845},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5262207984924316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4573504328727722},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.39438340067863464},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33668088912963867},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10429838299751282}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8451477289199829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7808628082275391},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7464830875396729},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6602673530578613},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6058841943740845},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5262207984924316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4573504328727722},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39438340067863464},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33668088912963867},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10429838299751282},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746227","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746227","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W2141440284","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2526425061","https://openalex.org/W2892009249","https://openalex.org/W2906383034","https://openalex.org/W2936774411","https://openalex.org/W2962778134","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963242190","https://openalex.org/W2964110616","https://openalex.org/W2981857663","https://openalex.org/W2989134874","https://openalex.org/W3035445001","https://openalex.org/W3095311338","https://openalex.org/W3096160024","https://openalex.org/W3097625183","https://openalex.org/W3097777922","https://openalex.org/W3097874139","https://openalex.org/W3097882114","https://openalex.org/W3162431424","https://openalex.org/W3162899666","https://openalex.org/W3164692279","https://openalex.org/W3169714379","https://openalex.org/W3196500669","https://openalex.org/W3198259287","https://openalex.org/W4385245566","https://openalex.org/W6629717138","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6680768788","https://openalex.org/W6713762819","https://openalex.org/W6739901393","https://openalex.org/W6754299077","https://openalex.org/W6757998062","https://openalex.org/W6770172821","https://openalex.org/W6774835902","https://openalex.org/W6779264309","https://openalex.org/W6784509666","https://openalex.org/W6801120842"],"related_works":["https://openalex.org/W2171218219","https://openalex.org/W1972271943","https://openalex.org/W2150410159","https://openalex.org/W4327525404","https://openalex.org/W4287185323","https://openalex.org/W3150905897","https://openalex.org/W1520183331","https://openalex.org/W2734842993","https://openalex.org/W2168175994","https://openalex.org/W3203142394"],"abstract_inverted_index":{"Non-autoregressive":[0],"transformer":[1],"(NAT)":[2],"based":[3,62],"speech":[4],"recognition":[5,137],"models":[6],"have":[7],"gained":[8],"more":[9,11],"and":[10,45,79,98,102,117,139,162,172,186,191],"attention":[12],"since":[13],"they":[14],"perform":[15],"faster":[16],"inference":[17,49],"speed":[18],"compared":[19],"with":[20,35,181],"autoregressive":[21],"counterparts,":[22],"especially":[23],"when":[24],"the":[25,31,41,72,75,80,94,99,110,113,118,126,144,149,160],"single-step":[26,32],"decoding":[27,33,42,140,150],"is":[28,69],"applied.":[29],"However,":[30],"process":[34],"length":[36,127],"prediction":[37,128],"will":[38],"suffer":[39],"from":[40],"stability":[43],"problem":[44],"limited":[46],"improvement":[47],"for":[48],"speed.":[50,141],"To":[51,142],"address":[52],"this,":[53],"in":[54,136],"this":[55],"paper,":[56],"we":[57,87,152],"propose":[58],"an":[59,89],"alignment":[60,90,106,114,122],"learning":[61],"NAT":[63],"model,":[64],"named":[65],"AL-NAT.":[66],"Our":[67,165],"idea":[68],"inspired":[70],"by":[71],"fact":[73],"that":[74],"encoder":[76,161],"CTC":[77,95],"output":[78,96],"target":[81,100],"sequence":[82],"are":[83],"monotonically":[84],"related.":[85],"Specifically,":[86],"design":[88],"cost":[91,115],"matrix":[92,116],"between":[93,112],"tokens":[97,101],"define":[103],"a":[104,182,187],"novel":[105],"loss":[107],"to":[108,147],"minimize":[109],"distance":[111],"ground":[119],"truth":[120],"monotonic":[121],"path.":[123],"By":[124],"eliminating":[125],"mechanism,":[129],"our":[130],"AL-NAT":[131],"model":[132,157],"achieves":[133,168],"remarkable":[134],"improvements":[135],"accuracy":[138],"learn":[143],"contextual":[145],"knowledge":[146],"improve":[148],"accuracy,":[151],"further":[153],"add":[154],"lightweight":[155,183],"language":[156],"on":[158,176,195],"both":[159],"decoder":[163],"side.":[164],"proposed":[166],"method":[167],"WERs":[169],"of":[170,174,189,193],"2.8%/6.3%":[171],"RTF":[173,192],"0.011":[175],"Librispeech":[177],"test":[178],"clean/other":[179],"sets":[180],"3-gram":[184],"LM,":[185,198],"CER":[188],"5.3%":[190],"0.005":[194],"Aishell1":[196],"without":[197],"respectively.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}